Assoc. Prof. Lei Chen
Shandong University, China
Speech
Title: Abnormal Behavior Detection and Action Localization
Based on Deep Learning
Abstract:: In recent years, the video surveillance systems are widely used in the fields of urban safety, security management, crime-fighting, and healthcare. The research on abnormal behavior and action localization is crucial to maintain safety and improve the quality of life. However, surveillance environments often present severe conditions, such as fluctuating lighting, the presence of shadows, and adverse weather conditions. These background variations introduce noises for human behavior features and degrades the abnormal behavior detection and action localization performance. To address these problems, we propose a new framework called efficient abnormal behavior detection that simultaneously integrates spatio-temporal feature modeling and long-term dependency modeling. And we design a multidimensional path aggregation network for spatio-temporal action location, which aggregates the features of multiple paths and fuses the corresponding hierarchical features to obtain spatio-temporal behavioural features. The experimental results show the effectiveness of our proposed methods and demonstrate superiority over other related methods. The research findings can be used to identify and intervene in potential threats, accidents, and dangerous situations.
Short bio: Lei Chen received the B.Sc.
and M.Sc. degrees in electrical
engineering from Shandong University,
Jinan, China, and the Ph.D. degree in
electrical and computer engineering from
University of Ottawa, Ontario, Canada.
He is currently an Associate Professor
with the School of Information Science
and Engineering, Shandong University,
China. His research interests include
image processing and computer vision,
visual quality assessment and pattern
recognition, machine learning and
artificial intelligence. He was the
principal investigator of projects
granted from the National Natural
Science Foundation of China, National
Natural Science Foundation of Shandong
Province, China Postdoctoral Science
Foundation, etc. He has published more
than 40 papers on top international
journals and conferences in recent years
including IEEE TIP, Signal Process.,
ICME, etc. He was awarded the Future
Plan for Young Scholars of Shandong
University. He served for many
international conferences including the
ICIGP 2021, CSAI2022, MLCCIM2022, and
ICIVC 2023 as Program Chair, Technical
Chair or Publicity Chair.
.
Assoc. Prof. Rui Chen
Tianjin University, China
Speech
Title: Old Photo Restoration Using Adaptive Energy Transition
of Latent Spaces
Abstract:: Recent old photo restoration works have achieved significant improvement using generative adversarial networks. However, the restoration quality under this generative framework is inevitably affected by the encoded properties of latent spaces, which reflect pivotal semantic information in the recovery process. Exploring the regularities in latent spaces is an important issue in restoration task. In this paper, we propose a novel Energy Transition Generative Adversarial Network (ET-GAN) for old photo restoration. Based on the fact that an energy function can capture the regularities in the data effectively, we propose to learn an energy-based prior model in latent spaces to improve the expressive power of GAN model. Moreover, we employ the Markov Chain Monte Carlo method to sample a batch of latent vectors from the prior distribution as the regularization. By linearly mixing with a regularized latent vector, the original latent vector is transformed along the principal semantic direction and a better latent space can be derived to improve the generation capability of ET-GAN to restore damaged photos with the multiple degradations. Extensive experiments demonstrate that our model can achieve the state-of-the-art performance in terms of numerical metrics and visual effects.
Short bio: Rui Chen received the Ph.D.
degree in instrument science from
Tsinghua University, China, in 2010. He
is currently an associate professor in
the School of Microelectronics, Tianjin
University. He has authored or
coauthored one book and over 70
technical articles in refereed journals
and proceedings. His current research
interests include generative artificial
intelligence technology and cognitive
theory.
.